© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 59059
    Prev
    Next
    INDEX
    Explanations

    you and pronouns for asking or telling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ours
    -0.18
     me
    -0.15
    ç»ĻæĪij
    -0.15
    让æĪij
    -0.14
     нами
    -0.14
     менÑı
    -0.13
     Yourself
    -0.13
     rám
    -0.12
     oneself
    -0.11
    ÅĽmy
    -0.11
    POSITIVE LOGITS
     you
    0.43
     вам
    0.36
     YOU
    0.31
    ä½łä»¬
    0.31
    you
    0.31
    ä½ł
    0.31
     Ihnen
    0.30
     você
    0.29
     bạn
    0.29
     vous
    0.28
    Activations Density 0.307%

    No Known Activations